training data

data_set_training.csv

@@ -232,3 +232,8 @@ MEMORIAL SATILLA HEALTH, 1900 TEBEAU ST, WAYCROSS, GA 31501|1900 TEBEAU STREET,
 VA MEDICAL CENTER 2002 HOLCOMBE BLVD, HOUSTON, TX 77030|VA MEDICAL CENTER 2002 HOLCOMBE BOULEVARD, HOUSTON, TX 77030|1
 VALLEY HEALTHCARE SYSTEM 1600 FORT BENNING RD, COLUMBUS, GA 31903|1600 FORT BENNING RD, COLUMBUS, GA 31903|1
 VALLEY HEALTHCARE SYSTEM 1600 FORT BENNING RD, COLUMBUS, GA 31903|1600 FORT BENNING RD, VALLEY HEALTHCARE SYSTEM, COLUMBUS, GA 31903|1
+315 22 BRAVERTON ST #110, EDGEWATER, MD 21037|315-22 BRAVERTON ST #110, EDGEWATER, MD 21037|1
+165 10 VILLAGE DR W, UPPER MARLBORO, MD 20772|165 12 VILLAGE DR W, UPPER MARLBORO, MD 20772|0
+345 12 OLD WASHINGTON RD, WALDORF, MD 20602|345-12 OLD WASHINGTON RD, WALDORF, MD 20602|1
+144 12 ONYX CT, FREDERICKSBURG, VA 22407|144-11 ONYX CT, FREDERICKSBURG, VA 22407|0
+144 12 ONYX CT, FREDERICKSBURG, VA 22407|144-12 ONYX CT, FREDERICKSBURG, VA 22407|1

dev_set_training.csv

@@ -24,4 +24,6 @@ ADDRESS1|ADDRESS2|ARE_SAME
 87-44 ROUTE 13, CORTLANDVILLE, NY 13045|87 24 ROUTE 13, CORTLANDVILLE, NY 13045|0
 872 ROUTE 13, CORTLANDVILLE, NY 13045|87-2 ROUTE 13, CORTLANDVILLE ,NY 13045|1
 8724 ROUTE 13, CORTLANDVILLE, NY 13045|87-24 ROUTE 13, CORTLANDVILLE, NY 13045|1
-HEART HEALTH, 90 N COLUMBUS AVE, LOUISVILLE, MS 39339|90 N COLUMBUS AVE, LOUISVILLE, MS 39339|1
+HEART HEALTH, 90 N COLUMBUS AVE, LOUISVILLE, MS 39339|90 N COLUMBUS AVE, LOUISVILLE, MS 39339|1
+115 34 SHOREWAY DR, QUEENSTOWN, MD 21658|115-43 SHOREWAY DR, QUEENSTOWN, MD 21658|0
+112 24 SHOREWAY DR, QUEENSTOWN, MD 21658|112-24 SHOREWAY DR, QUEENSTOWN, MD 21658|1

quick_evaluate.py

@@ -19,22 +19,27 @@ def get_sbert_embedding(input_text):
     embedding = model_sbert.encode(input_text)
     return embedding.tolist()
 
-a1 = "65 Mountain Blvd Ext, Warren, NJ 07059"
-a2 = "112 Mountain Blvd Ext, Warren, NJ 07059"
-a3 = "1677 NJ-27 #2, Edison, NJ 08817"
-a4 = "5078 S Maryland Pkwy, Las Vegas, NV 89119"
-a5 = "65 Mountain Boulevard Ext, Warren, NJ 07059"
-a6 = "123 Broad St, New York, NY, 10304-2345"
-a7 = "440 TECHNOLOGY CENTER DRIVE, Boston, MA 10034"
-a8 = "200 Technology Center Drive, Boston, MA 10034"
-a8x= "87 Technology Center Drive, Boston, MA 10034"
-a9 = "440 Technology Center Dr., Boston, MA 10034-0345"
-a10 = "440 Technology Center Dr., Boston, MA 10034"
-a11="872 Route 13, Cortlandville NY 13045"
-a12="87-2 Route 13, Cortlandville NY 13045"
-a13="87-5 Route 13, Cortlandville NY 13045"
-a14="257 37 US Rt 11, Evans Mills NY 13637"
-a15="257-37 US Route 11, Evans Mills NY 13637"
+a1 = "65 MOUNTAIN BLVD EXT, WARREN, NJ 07059"
+a2 = "112 MOUNTAIN BLVD EXT, WARREN, NJ 07059"
+a3 = "1677 NJ-27 #2, EDISON, NJ 08817"
+a4 = "5078 S MARYLAND PKWY, LAS VEGAS, NV 89119"
+a5 = "65 MOUNTAIN BOULEVARD EXT, WARREN, NJ 07059"
+a6 = "123 BROAD ST, NEW YORK, NY, 10304-2345"
+a7 = "440 TECHNOLOGY CENTER DRIVE, BOSTON, MA 10034"
+a8 = "200 TECHNOLOGY CENTER DRIVE, BOSTON, MA 10034"
+a8x= "87 TECHNOLOGY CENTER DRIVE, BOSTON, MA 10034"
+#a9 = "440 TECHNOLOGY CENTER DR., BOSTON, MA 10034"
+a10= "440 TECHNOLOGY CENTER DR., BOSTON, MA 10034"
+a11="87-22 ROUTE 13, CORTLANDVILLE, NY 13045"
+a12="87 22 ROUTE 13, CORTLANDVILLE, NY 13045"
+a13="87-55 ROUTE 13, CORTLANDVILLE, NY 13045"
+a14="257 37 US RT 11, EVANS MILLS, NY 13637"
+a15="257-37 US ROUTE 11, EVANS MILLS, NY 13637"
+
+a16="15645 S MAIN ST SUITE D, PENNINGTON, NJ 08534"
+a17="156-45 S MAIN ST SUITE D, PENNINGTON, NJ 08534"
+a18="156-46 S MAIN ST SUITE D, PENNINGTON, NJ 08534"
+
 #def get_embedding(input_text):
 #    encoded_input = tokenizer(input_text, return_tensors='pt')
 #    input_ids = encoded_input.input_ids
@@ -63,7 +68,7 @@ e6 = get_sbert_embedding(a6)
 e7 = get_sbert_embedding(a7)
 e8 = get_sbert_embedding(a8)
 e8x = get_sbert_embedding(a8x)
-e9 = get_sbert_embedding(a9)
+#e9 = get_sbert_embedding(a9)
 e10 = get_sbert_embedding(a10)
 e11 = get_sbert_embedding(a11)
 e12 = get_sbert_embedding(a12)
@@ -71,6 +76,10 @@ e13 = get_sbert_embedding(a13)
 e14 = get_sbert_embedding(a14)
 e15 = get_sbert_embedding(a15)
 
+e16 = get_sbert_embedding(a16)
+e17 = get_sbert_embedding(a17)
+e18 = get_sbert_embedding(a18)
+
 print(f"a1 \"{a1}\" to \"{a2}\" a2 - expected Different")
 print(cosine_similarity([e1], [e2]))
 print(f"a1 \"{a1}\" to \"{a4}\" a4 - expected Different")
@@ -83,8 +92,8 @@ print(cosine_similarity([e7], [e8]))
 print(f"a7 \"{a7}\" to \"{a8x}\" a8x - expected Different")
 print(cosine_similarity([e7], [e8x]))
 
-print(f"a7 \"{a7}\" to \"{a9}\" a9 - expected Same")
-print(cosine_similarity([e7], [e9]))
+#print(f"a7 \"{a7}\" to \"{a9}\" a9 - expected Same")
+#print(cosine_similarity([e7], [e9]))
 
 print(f"a7 \"{a7}\" to \"{a10}\" a10 - expected Same")
 print(cosine_similarity([e7], [e10]))
@@ -97,6 +106,13 @@ print(cosine_similarity([e11], [e13]))
 
 print(f"a14 \"{a14}\" to \"{a15}\" a15 - expected Same")
 print(cosine_similarity([e14], [e15]))
+
+print(f"a16 \"{a16}\" to \"{a17}\" a17 - expected Same")
+print(cosine_similarity([e16], [e17]))
+
+print(f"a16 \"{a16}\" to \"{a18}\" a18 - expected Different")
+print(cosine_similarity([e16], [e18]))
+
 # with base
 #a1 to a2
 #[[0.99512167]]